相关论文: Multi-view dense image matching with similarity le…

Multi-view clustering has attracted increasing attentions recently by utilizing information from multiple views. However, existing multi-view clustering methods are either with high computation and space complexities, or lack of…

Large-scale contrastive pre-training produces powerful Vision-and-Language Models (VLMs) capable of generating representations (embeddings) effective for a wide variety of visual and multimodal tasks. However, these pretrained embeddings…

This paper fosters the idea that deep learning methods can be used to complement classical visual odometry pipelines to improve their accuracy and to associate uncertainty models to their estimations. We show that the biases inherent to the…

For convolutional neural network models that optimize an image embedding, we propose a method to highlight the regions of images that contribute most to pairwise similarity. This work is a corollary to the visualization tools developed for…

3D reconstruction from a single RGB image is a challenging problem in computer vision. Previous methods are usually solely data-driven, which lead to inaccurate 3D shape recovery and limited generalization capability. In this work, we focus…

Monocular dense 3D reconstruction of deformable objects is a hard ill-posed problem in computer vision. Current techniques either require dense correspondences and rely on motion and deformation cues, or assume a highly accurate…

Digital Elevation Models (DEMs) are vital datasets for geospatial applications such as hydrological modeling and environmental monitoring. However, conventional methods to generate DEM, such as using LiDAR and photogrammetry, require…

Deep learning affords enormous opportunities to augment the armamentarium of biomedical imaging, albeit its design and implementation have potential flaws. Fundamentally, most deep learning models are driven entirely by data without…

End-to-end deep learning methods have advanced stereo vision in recent years and obtained excellent results when the training and test data are similar. However, large datasets of diverse real-world scenes with dense ground truth are…

Homography estimation is an important task in computer vision applications, such as image stitching, video stabilization, and camera calibration. Traditional homography estimation methods heavily depend on the quantity and distribution of…

Feed-forward 3D reconstruction models such as DUSt3R, VGGT, and Depth Anything 3 (DA3) are transformer-based foundation models that infer camera geometry and dense scene structure in a single forward pass. Trained at scale in a supervised…

Multi-view image generation holds significant application value in computer vision, particularly in domains like 3D reconstruction, virtual reality, and augmented reality. Most existing methods, which rely on extending single images, face…

This paper addresses the problem of Monocular Depth Estimation (MDE). Existing approaches on MDE usually model it as a pixel-level regression problem, ignoring the underlying geometry property. We empirically find this may result in…

We present a method for depth estimation with monocular images, which can predict high-quality depth on diverse scenes up to an affine transformation, thus preserving accurate shapes of a scene. Previous methods that predict metric depth…

Point cloud based 3D deep model has wide applications in many applications such as autonomous driving, house robot, and so on. Inspired by the recent prompt learning in natural language processing, this work proposes a novel Multi-view…

Disparity prediction from stereo images is essential to computer vision applications including autonomous driving, 3D model reconstruction, and object detection. To predict accurate disparity map, we propose a novel deep learning…

Multi-view product image queries can improve retrieval performance over single view queries significantly. In this paper, we investigated the performance of deep convolutional neural networks (ConvNets) on multi-view product image search.…

Diffusion-based approaches have recently demonstrated strong performance for single-image novel view synthesis by conditioning generative models on geometry inferred from monocular depth estimation. However, in practice, the quality and…

Learning-based multi-view stereo (MVS) methods deal with predicting accurate depth maps to achieve an accurate and complete 3D representation. Despite the excellent performance, existing methods ignore the fact that a suitable depth…

Modern optical satellite sensors enable high-resolution stereo reconstruction from space. But the challenging imaging conditions when observing the Earth from space push stereo matching to its limits. In practice, the resulting digital…